CONFLICTING DATA HIDDEN

CONFLICTING DATA HIDDEN BY UNJUSTIFIED PROJECTIONS

PART TWO OF THE NEPC REPORT ON DR. CHETTY’S RESEARCH

In reanalyzing the Chetty research report, Moshe Adler of Columbia University found conflicting data that was ignored, perhaps because it contradicted the initial report’s conclusion. 

“The existence of a crucial conflicting result was not mentioned in the revised report.” (Page 3)

“An earlier version of the report found that an increase in teacher value-added has no effect on income at age 30, but this result is not mentioned in this revised version. Instead, the authors state that they did not have a sufficiently large sample to investigate the relationship between teacher value-added and income at any age after 28, but this claim is untrue. They had 220,000 observations (p. 15), which is a more than sufficiently large sample for their analysis.” (page 3)

While it is true the sample for 30 years olds was smaller, at 61,639 observations the data sample is more than sufficient for the purposes of this analysis.  Yet it was dropped from the revised report.

Not only did the Chetty report ignore that data, it chose to project the results of their conclusions onto “any subsequent age group” (page 4), which would include the 30 year olds for whom they had contradictory data.  Adler refers to that projection as “unjustified”. (page 4)

It would appear that Chetty not only withheld contradictory information, but he may have substituted in its place conflicting data that supported the original conclusions.  That does not strike me as professional.